Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

/pdf/reinforcement-learning-an-introduction-rzxgej9p17.pdf

Reinforcement Learning: An Introduction

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

The neural basis of drug craving: An incentive-sensitization theory of addiction

This article opens by noting that positive emotions do not fit existing models of emotions. Consequently, a new model is advanced to describe the form and function of a subset of positive emotions, including joy, interest, contentment, and love. This new model posits that these positive emotions serve to broaden an individual's momentary thought-action repertoire, which in turn has the effect of building that individual's physical, intellectual, and social resources. Empirical evidence to support this broadenand-build model of positive emotions is reviewed, and implications for emotion regulation and health promotion are discussed. Even though research on emotions has this new perspective are featured. My hope is flourished in recent years, investigations that that this article will unlock scientific curiosity expressly target positive emotions remain few and far between. Any review of the psychological literature on emotions will show that psychologists have typically favored negative emotions in theory building and hypothesis testing. In so doing, psychologists have inadvertently marginalized the emotions, such as joy, about positive emotions, not only to test the ideas presented here, but also to build other new models that might illuminate the nature and value of positive emotions. Psychology sorely needs more studies on positive emotions, not simply to level the uneven knowledge bases between negative and positive emotions, but interest, contentment, and love, that share a more critically, to guide applications and pleasant subjective feel. To date, then, psychology's knowledge base regarding positive emotions is so thin that satisfying answers to the question "What good are positive emotions?" have yet to be articulated. This is unfortunate. Experiences of positive emotion are central to human nature and contribute richly to the quality of people's lives (Diener & Larsen,

http://www.gruberpeplab.com/teaching/psych3131_spring2015/documents/15.1_Fredrickson1998_WhatGoodarePositiveEmotions.pdf

What Good Are Positive Emotions

The adolescent brain and age-related behavioral manifestations

https://lsa.umich.edu/psych/research&labs/berridge/publications/Berridge&RobinsonBrResRev1998.pdf

What is the role of dopamine in reward: hedonic impact, reward learning, or incentive salience?

Introduction
Debate continues over the precise causal contribution made by mesolimbic dopamine systems to reward. There are three competing explanatory categories: ‘liking’, learning, and ‘wanting’. Does dopamine mostly mediate the hedonic impact of reward (‘liking’)? Does it instead mediate learned predictions of future reward, prediction error teaching signals and stamp in associative links (learning)? Or does dopamine motivate the pursuit of rewards by attributing incentive salience to reward-related stimuli (‘wanting’)? Each hypothesis is evaluated here, and it is suggested that the incentive salience or ‘wanting’ hypothesis of dopamine function may be consistent with more evidence than either learning or ‘liking’. In brief, recent evidence indicates that dopamine is neither necessary nor sufficient to mediate changes in hedonic ‘liking’ for sensory pleasures. Other recent evidence indicates that dopamine is not needed for new learning, and not sufficient to directly mediate learning by causing teaching or prediction signals. By contrast, growing evidence indicates that dopamine does contribute causally to incentive salience. Dopamine appears necessary for normal ‘wanting’, and dopamine activation can be sufficient to enhance cue-triggered incentive salience. Drugs of abuse that promote dopamine signals short circuit and sensitize dynamic mesolimbic mechanisms that evolved to attribute incentive salience to rewards. Such drugs interact with incentive salience integrations of Pavlovian associative information with physiological state signals. That interaction sets the stage to cause compulsive ‘wanting’ in addiction, but also provides opportunities for experiments to disentangle ‘wanting’, ‘liking’, and learning hypotheses. Results from studies that exploited those opportunities are described here.

/pdf/the-debate-over-dopamine-s-role-in-reward-the-case-for-2f5liljkhc.pdf

The debate over dopamine’s role in reward: the case for incentive salience

Food reward: Brain substrates of wanting and liking

https://www.wisebrain.org/media/Papers/BerridgeRobinson%26AldridgeDissectingcomponentsofrewardCurrentOpinPharm2009.pdf

Kent C. Berridge

Papers

The neural basis of drug craving: An incentive-sensitization theory of addiction

What is the role of dopamine in reward: hedonic impact, reward learning, or incentive salience?

The debate over dopamine’s role in reward: the case for incentive salience

Food reward: Brain substrates of wanting and liking

Dissecting components of reward: 'liking', 'wanting', and learning.